Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    quantitative estimates, particularly those involving the word "approximately."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     voller
    -0.52
    شهاد
    -0.51
     ());
    -0.50
    Jährige
    -0.50
    humidité
    -0.50
    !");
    -0.49
     מלא
    -0.48
    MULTI
    -0.48
    !';
    -0.47
    vogel
    -0.46
    POSITIVE LOGITS
     roughly
    1.06
     ungefähr
    0.98
     Roughly
    0.96
     approxim
    0.95
     approx
    0.93
     approximately
    0.92
     ungefär
    0.92
    Around
    0.92
    eabouts
    0.90
    roughly
    0.90
    Act Density 0.215%

    No Known Activations